MO-01 - Adding CSV backend support

CITATION.cff

@@ -2,14 +2,9 @@
 # Visit https://bit.ly/cffinit to generate yours today!
 
 cff-version: 1.2.0
-title: Docling
-message: 'If you use Docling, please consider citing as below.'
+title: Dockowling
+message: 'If you use Dockowling, please consider citing as below.'
 type: software
 authors:
-  - name: Docling Team
-identifiers:
-  - type: url
-    value: 'https://arxiv.org/abs/2408.09869'
-    description: 'arXiv:2408.09869'
-repository-code: 'https://github.com/DS4SD/docling'
+  - name: Docowling
 license: MIT

Dockerfile

@@ -17,7 +17,7 @@ ENV TORCH_HOME=/tmp/
 COPY docs/examples/minimal.py /root/minimal.py
 
 RUN python -c 'from deepsearch_glm.utils.load_pretrained_models import load_pretrained_nlp_models; load_pretrained_nlp_models(verbose=True);'
-RUN python -c 'from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline; StandardPdfPipeline.download_models_hf(force=True);'
+RUN python -c 'from docowling.pipeline.standard_pdf_pipeline import StandardPdfPipeline; StandardPdfPipeline.download_models_hf(force=True);'
 
 # On container environments, always set a thread budget to avoid undesired thread congestion.
 ENV OMP_NUM_THREADS=4

README.md

@@ -1,5 +1,5 @@
 <p align="center">
-  <a href="https://github.com/ds4sd/docling">
+  <a href="https://github.com/mouraworks/docowling">
     <img loading="lazy" alt="Docling" src="https://github.com/mouraworks/docowling/blob/main/docs/assets/docowling.png" width="80%"/>
   </a>
 </p>

docowling/backend/abstract_backend.py

@@ -6,8 +6,8 @@ from typing import TYPE_CHECKING, Set, Union
 from docling_core.types.doc import DoclingDocument
 
 if TYPE_CHECKING:
-    from docling.datamodel.base_models import InputFormat
-    from docling.datamodel.document import InputDocument
+    from docowling.datamodel.base_models import InputFormat
+    from docowling.datamodel.document import InputDocument
 
 
 class AbstractDocumentBackend(ABC):

docowling/backend/asciidoc_backend.py

@@ -16,9 +16,9 @@ from docling_core.types.doc import (
     TableData,
 )
 
-from docling.backend.abstract_backend import DeclarativeDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.backend.abstract_backend import DeclarativeDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/backend/csv_backend.py

@@ -0,0 +1,105 @@
+import csv
+from io import StringIO
+from pathlib import Path
+from typing import Union, Dict, Tuple, List
+
+from docling_core.types.doc import (
+    DoclingDocument,
+    DocumentOrigin,
+    GroupLabel,
+    TableData,
+    TableCell,
+)
+from docowling.backend.abstract_backend import DeclarativeDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
+
+
+class CsvDocumentBackend(DeclarativeDocumentBackend):
+    def __init__(self, in_doc: "InputDocument", path_or_stream: Union[StringIO, Path]):
+        super().__init__(in_doc, path_or_stream)
+        self.rows = []
+        try:
+            # Load the CSV data
+            if isinstance(self.path_or_stream, Path):
+                with self.path_or_stream.open(mode="r", encoding="utf-8") as file:
+                    self.rows = list(csv.reader(file))
+            elif isinstance(self.path_or_stream, StringIO):
+                self.rows = list(csv.reader(self.path_or_stream))
+
+            self.valid = True
+        except Exception as e:
+            self.valid = False
+            raise RuntimeError(
+                f"CsvDocumentBackend could not load document with hash {self.document_hash}"
+            ) from e
+
+    def is_valid(self) -> bool:
+        return self.valid
+
+    @classmethod
+    def supports_pagination(cls) -> bool:
+        return False  # Typically, CSV files do not support pagination.
+
+    def unload(self):
+        self.path_or_stream = None
+
+    @classmethod
+    def supported_formats(cls) -> Set[InputFormat]:
+        return {InputFormat.CSV}
+
+    def convert(self) -> DoclingDocument:
+        origin = DocumentOrigin(
+            filename=self.file.name or "file.csv",
+            mimetype="text/csv",
+            binary_hash=self.document_hash,
+        )
+        doc = DoclingDocument(name=self.file.stem or "file.csv", origin=origin)
+
+        if self.is_valid():
+            doc = self._convert_csv_to_document(doc)
+        else:
+            raise RuntimeError(
+                f"Cannot convert doc with {self.document_hash} because the backend failed to init."
+            )
+
+        return doc
+
+    def _convert_csv_to_document(self, doc: DoclingDocument) -> DoclingDocument:
+        if not self.rows:
+            return doc  # No data to process
+
+        # Create a section for the CSV data
+        self.parents[0] = doc.add_group(
+            parent=None,
+            label=GroupLabel.SECTION,
+            name="CSV Data",
+        )
+
+        # Convert rows into table data
+        num_rows = len(self.rows)
+        num_cols = max(len(row) for row in self.rows)
+
+        table_data = TableData(
+            num_rows=num_rows,
+            num_cols=num_cols,
+            table_cells=[],
+        )
+
+        for row_idx, row in enumerate(self.rows):
+            for col_idx, cell in enumerate(row):
+                table_cell = TableCell(
+                    text=cell,
+                    row_span=1,
+                    col_span=1,
+                    start_row_offset_idx=row_idx,
+                    end_row_offset_idx=row_idx + 1,
+                    start_col_offset_idx=col_idx,
+                    end_col_offset_idx=col_idx + 1,
+                    col_header=False,
+                    row_header=False,
+                )
+                table_data.table_cells.append(table_cell)
+
+        doc.add_table(data=table_data, parent=self.parents[0])
+        return doc

docowling/backend/docling_parse_backend.py

@@ -10,9 +10,9 @@ from docling_parse.pdf_parsers import pdf_parser_v1
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage
 
-from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
-from docling.datamodel.base_models import Cell
-from docling.datamodel.document import InputDocument
+from docowling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
+from docowling.datamodel.base_models import Cell
+from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/backend/docling_parse_v2_backend.py

@@ -10,11 +10,11 @@ from docling_parse.pdf_parsers import pdf_parser_v2
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage
 
-from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
-from docling.datamodel.base_models import Cell, Size
+from docowling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
+from docowling.datamodel.base_models import Cell, Size
 
 if TYPE_CHECKING:
-    from docling.datamodel.document import InputDocument
+    from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/backend/html_backend.py

@@ -13,9 +13,9 @@ from docling_core.types.doc import (
     TableData,
 )
 
-from docling.backend.abstract_backend import DeclarativeDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.backend.abstract_backend import DeclarativeDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/backend/md_backend.py

@@ -19,9 +19,9 @@ from docling_core.types.doc import (
 )
 from marko import Markdown
 
-from docling.backend.abstract_backend import DeclarativeDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.backend.abstract_backend import DeclarativeDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/backend/msexcel_backend.py

@@ -18,9 +18,9 @@ from openpyxl.cell.cell import Cell
 from openpyxl.drawing.image import Image
 from openpyxl.worksheet.worksheet import Worksheet
 
-from docling.backend.abstract_backend import DeclarativeDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.backend.abstract_backend import DeclarativeDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/backend/mspowerpoint_backend.py

@@ -20,12 +20,12 @@ from PIL import Image
 from pptx import Presentation
 from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
 
-from docling.backend.abstract_backend import (
+from docowling.backend.abstract_backend import (
     DeclarativeDocumentBackend,
     PaginatedDocumentBackend,
 )
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/backend/msword_backend.py

@@ -18,9 +18,9 @@ from lxml import etree
 from lxml.etree import XPath
 from PIL import Image, UnidentifiedImageError
 
-from docling.backend.abstract_backend import DeclarativeDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.backend.abstract_backend import DeclarativeDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/backend/pdf_backend.py

@@ -6,9 +6,9 @@ from typing import Iterable, Optional, Set, Union
 from docling_core.types.doc import BoundingBox, Size
 from PIL import Image
 
-from docling.backend.abstract_backend import PaginatedDocumentBackend
-from docling.datamodel.base_models import Cell, InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.backend.abstract_backend import PaginatedDocumentBackend
+from docowling.datamodel.base_models import Cell, InputFormat
+from docowling.datamodel.document import InputDocument
 
 
 class PdfPageBackend(ABC):

docowling/backend/pypdfium2_backend.py

@@ -11,11 +11,11 @@ from PIL import Image, ImageDraw
 from pypdfium2 import PdfTextPage
 from pypdfium2._helpers.misc import PdfiumError
 
-from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
-from docling.datamodel.base_models import Cell
+from docowling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
+from docowling.datamodel.base_models import Cell
 
 if TYPE_CHECKING:
-    from docling.datamodel.document import InputDocument
+    from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/backend/xml/pubmed_backend.py

@@ -16,9 +16,9 @@ from docling_core.types.doc import (
 from lxml import etree
 from typing_extensions import TypedDict, override
 
-from docling.backend.abstract_backend import DeclarativeDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.backend.abstract_backend import DeclarativeDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/backend/xml/uspto_backend.py

@@ -30,9 +30,9 @@ from docling_core.types.doc.document import LevelNumber
 from pydantic import NonNegativeInt
 from typing_extensions import Self, TypedDict, override
 
-from docling.backend.abstract_backend import DeclarativeDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.backend.abstract_backend import DeclarativeDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docowling/cli/main.py

@@ -14,18 +14,18 @@ from docling_core.types.doc import ImageRefMode
 from docling_core.utils.file import resolve_source_to_path
 from pydantic import TypeAdapter, ValidationError
 
-from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
-from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
-from docling.backend.pdf_backend import PdfDocumentBackend
-from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
-from docling.datamodel.base_models import (
+from docowling.backend.docling_parse_backend import DoclingParseDocumentBackend
+from docowling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
+from docowling.backend.pdf_backend import PdfDocumentBackend
+from docowling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
+from docowling.datamodel.base_models import (
     ConversionStatus,
     FormatToExtensions,
     InputFormat,
     OutputFormat,
 )
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import (
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import (
     AcceleratorDevice,
     AcceleratorOptions,
     EasyOcrOptions,
@@ -39,8 +39,8 @@ from docling.datamodel.pipeline_options import (
     TesseractCliOcrOptions,
     TesseractOcrOptions,
 )
-from docling.datamodel.settings import settings
-from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
+from docowling.datamodel.settings import settings
+from docowling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
 
 warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|torch")
 warnings.filterwarnings(action="ignore", category=FutureWarning, module="easyocr")

docowling/datamodel/base_models.py

@@ -15,7 +15,7 @@ from PIL.Image import Image
 from pydantic import BaseModel, ConfigDict
 
 if TYPE_CHECKING:
-    from docling.backend.pdf_backend import PdfPageBackend
+    from docowling.backend.pdf_backend import PdfPageBackend
 
 
 class ConversionStatus(str, Enum):
@@ -39,6 +39,7 @@ class InputFormat(str, Enum):
     ASCIIDOC = "asciidoc"
     MD = "md"
     XLSX = "xlsx"
+    CSV = "csv"
     XML_USPTO = "xml_uspto"
 
 
@@ -60,6 +61,7 @@ FormatToExtensions: Dict[InputFormat, List[str]] = {
     InputFormat.IMAGE: ["jpg", "jpeg", "png", "tif", "tiff", "bmp"],
     InputFormat.ASCIIDOC: ["adoc", "asciidoc", "asc"],
     InputFormat.XLSX: ["xlsx"],
+    InputFormat.CSV: ["csv"],
     InputFormat.XML_USPTO: ["xml", "txt"],
 }
 
@@ -88,6 +90,7 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
     InputFormat.XLSX: [
         "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
     ],
+    InputFormat.CSV: ["text/csv"],
     InputFormat.XML_USPTO: ["application/xml", "text/plain"],
 }
 

docowling/datamodel/document.py

@@ -47,11 +47,11 @@ from docling_core.utils.legacy import docling_document_to_legacy
 from pydantic import BaseModel
 from typing_extensions import deprecated
 
-from docling.backend.abstract_backend import (
+from docowling.backend.abstract_backend import (
     AbstractDocumentBackend,
     PaginatedDocumentBackend,
 )
-from docling.datamodel.base_models import (
+from docowling.datamodel.base_models import (
     AssembledUnit,
     ConversionStatus,
     DocumentStream,
@@ -62,12 +62,12 @@ from docling.datamodel.base_models import (
     MimeTypeToFormat,
     Page,
 )
-from docling.datamodel.settings import DocumentLimits
-from docling.utils.profiling import ProfilingItem
-from docling.utils.utils import create_file_hash, create_hash
+from docowling.datamodel.settings import DocumentLimits
+from docowling.utils.profiling import ProfilingItem
+from docowling.utils.utils import create_file_hash, create_hash
 
 if TYPE_CHECKING:
-    from docling.document_converter import FormatOption
+    from docowling.document_converter import FormatOption
 
 _log = logging.getLogger(__name__)
 

docowling/document_converter.py

@@ -7,35 +7,36 @@ from typing import Dict, Iterable, Iterator, List, Optional, Type, Union
 
 from pydantic import BaseModel, ConfigDict, model_validator, validate_call
 
-from docling.backend.abstract_backend import AbstractDocumentBackend
-from docling.backend.asciidoc_backend import AsciiDocBackend
-from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
-from docling.backend.html_backend import HTMLDocumentBackend
-from docling.backend.md_backend import MarkdownDocumentBackend
-from docling.backend.msexcel_backend import MsExcelDocumentBackend
-from docling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
-from docling.backend.msword_backend import MsWordDocumentBackend
-from docling.backend.xml.pubmed_backend import PubMedDocumentBackend
-from docling.backend.xml.uspto_backend import PatentUsptoDocumentBackend
-from docling.datamodel.base_models import (
+from docowling.backend.abstract_backend import AbstractDocumentBackend
+from docowling.backend.asciidoc_backend import AsciiDocBackend
+from docowling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
+from docowling.backend.html_backend import HTMLDocumentBackend
+from docowling.backend.md_backend import MarkdownDocumentBackend
+from docowling.backend.msexcel_backend import MsExcelDocumentBackend
+from docowling.backend.csv_backend import CsvDocumentBackend
+from docowling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
+from docowling.backend.msword_backend import MsWordDocumentBackend
+from docowling.backend.xml.pubmed_backend import PubMedDocumentBackend
+from docowling.backend.xml.uspto_backend import PatentUsptoDocumentBackend
+from docowling.datamodel.base_models import (
     ConversionStatus,
     DoclingComponentType,
     DocumentStream,
     ErrorItem,
     InputFormat,
 )
-from docling.datamodel.document import (
+from docowling.datamodel.document import (
     ConversionResult,
     InputDocument,
     _DocumentConversionInput,
 )
-from docling.datamodel.pipeline_options import PipelineOptions
-from docling.datamodel.settings import DocumentLimits, settings
-from docling.exceptions import ConversionError
-from docling.pipeline.base_pipeline import BasePipeline
-from docling.pipeline.simple_pipeline import SimplePipeline
-from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
-from docling.utils.utils import chunkify
+from docowling.datamodel.pipeline_options import PipelineOptions
+from docowling.datamodel.settings import DocumentLimits, settings
+from docowling.exceptions import ConversionError
+from docowling.pipeline.base_pipeline import BasePipeline
+from docowling.pipeline.simple_pipeline import SimplePipeline
+from docowling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
+from docowling.utils.utils import chunkify
 
 _log = logging.getLogger(__name__)
 
@@ -58,6 +59,9 @@ class ExcelFormatOption(FormatOption):
     pipeline_cls: Type = SimplePipeline
     backend: Type[AbstractDocumentBackend] = MsExcelDocumentBackend
 
+class CsvFormatOption(FormatOption):
+    pipeline_cls: Type = SimplePipeline
+    backend: Type[AbstractDocumentBackend] = CsvDocumentBackend
 
 class WordFormatOption(FormatOption):
     pipeline_cls: Type = SimplePipeline
@@ -109,6 +113,9 @@ def _get_default_option(format: InputFormat) -> FormatOption:
         InputFormat.XLSX: FormatOption(
             pipeline_cls=SimplePipeline, backend=MsExcelDocumentBackend
         ),
+        InputFormat.CSV: FormatOption(
+            pipeline_cls=SimplePipeline, backend=CsvDocumentBackend
+        ),
         InputFormat.DOCX: FormatOption(
             pipeline_cls=SimplePipeline, backend=MsWordDocumentBackend
         ),

docowling/models/base_model.py

@@ -3,8 +3,8 @@ from typing import Any, Iterable
 
 from docling_core.types.doc import DoclingDocument, NodeItem
 
-from docling.datamodel.base_models import Page
-from docling.datamodel.document import ConversionResult
+from docowling.datamodel.base_models import Page
+from docowling.datamodel.document import ConversionResult
 
 
 class BasePageModel(ABC):

docowling/models/base_ocr_model.py

@@ -10,11 +10,11 @@ from PIL import Image, ImageDraw
 from rtree import index
 from scipy.ndimage import find_objects, label
 
-from docling.datamodel.base_models import Cell, OcrCell, Page
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import OcrOptions
-from docling.datamodel.settings import settings
-from docling.models.base_model import BasePageModel
+from docowling.datamodel.base_models import Cell, OcrCell, Page
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import OcrOptions
+from docowling.datamodel.settings import settings
+from docowling.models.base_model import BasePageModel
 
 _log = logging.getLogger(__name__)
 

docowling/models/ds_glm_model.py

@@ -24,18 +24,18 @@ from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocu
 from PIL import ImageDraw
 from pydantic import BaseModel, ConfigDict, TypeAdapter
 
-from docling.datamodel.base_models import (
+from docowling.datamodel.base_models import (
     Cluster,
     ContainerElement,
     FigureElement,
     Table,
     TextElement,
 )
-from docling.datamodel.document import ConversionResult, layout_label_to_ds_type
-from docling.datamodel.settings import settings
-from docling.utils.glm_utils import to_docling_document
-from docling.utils.profiling import ProfilingScope, TimeRecorder
-from docling.utils.utils import create_hash
+from docowling.datamodel.document import ConversionResult, layout_label_to_ds_type
+from docowling.datamodel.settings import settings
+from docowling.utils.glm_utils import to_docling_document
+from docowling.utils.profiling import ProfilingScope, TimeRecorder
+from docowling.utils.utils import create_hash
 
 
 class GlmOptions(BaseModel):

docowling/models/easyocr_model.py

@@ -6,17 +6,17 @@ import numpy
 import torch
 from docling_core.types.doc import BoundingBox, CoordOrigin
 
-from docling.datamodel.base_models import Cell, OcrCell, Page
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import (
+from docowling.datamodel.base_models import Cell, OcrCell, Page
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import (
     AcceleratorDevice,
     AcceleratorOptions,
     EasyOcrOptions,
 )
-from docling.datamodel.settings import settings
-from docling.models.base_ocr_model import BaseOcrModel
-from docling.utils.accelerator_utils import decide_device
-from docling.utils.profiling import TimeRecorder
+from docowling.datamodel.settings import settings
+from docowling.models.base_ocr_model import BaseOcrModel
+from docowling.utils.accelerator_utils import decide_device
+from docowling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
 

docowling/models/layout_model.py

@@ -9,20 +9,20 @@ from docling_core.types.doc import CoordOrigin, DocItemLabel
 from docling_ibm_models.layoutmodel.layout_predictor import LayoutPredictor
 from PIL import Image, ImageDraw, ImageFont
 
-from docling.datamodel.base_models import (
+from docowling.datamodel.base_models import (
     BoundingBox,
     Cell,
     Cluster,
     LayoutPrediction,
     Page,
 )
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import AcceleratorDevice, AcceleratorOptions
-from docling.datamodel.settings import settings
-from docling.models.base_model import BasePageModel
-from docling.utils.accelerator_utils import decide_device
-from docling.utils.layout_postprocessor import LayoutPostprocessor
-from docling.utils.profiling import TimeRecorder
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import AcceleratorDevice, AcceleratorOptions
+from docowling.datamodel.settings import settings
+from docowling.models.base_model import BasePageModel
+from docowling.utils.accelerator_utils import decide_device
+from docowling.utils.layout_postprocessor import LayoutPostprocessor
+from docowling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
 

docowling/models/ocr_mac_model.py

@@ -4,12 +4,12 @@ from typing import Iterable, Optional, Tuple
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
 
-from docling.datamodel.base_models import OcrCell, Page
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import OcrMacOptions
-from docling.datamodel.settings import settings
-from docling.models.base_ocr_model import BaseOcrModel
-from docling.utils.profiling import TimeRecorder
+from docowling.datamodel.base_models import OcrCell, Page
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import OcrMacOptions
+from docowling.datamodel.settings import settings
+from docowling.models.base_ocr_model import BaseOcrModel
+from docowling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
 

docowling/models/page_assemble_model.py

@@ -4,7 +4,7 @@ from typing import Iterable, List
 
 from pydantic import BaseModel
 
-from docling.datamodel.base_models import (
+from docowling.datamodel.base_models import (
     AssembledUnit,
     ContainerElement,
     FigureElement,
@@ -13,10 +13,10 @@ from docling.datamodel.base_models import (
     Table,
     TextElement,
 )
-from docling.datamodel.document import ConversionResult
-from docling.models.base_model import BasePageModel
-from docling.models.layout_model import LayoutModel
-from docling.utils.profiling import TimeRecorder
+from docowling.datamodel.document import ConversionResult
+from docowling.models.base_model import BasePageModel
+from docowling.models.layout_model import LayoutModel
+from docowling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
 

docowling/models/page_preprocessing_model.py

@@ -4,11 +4,11 @@ from typing import Iterable, Optional
 from PIL import ImageDraw
 from pydantic import BaseModel
 
-from docling.datamodel.base_models import Page
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.settings import settings
-from docling.models.base_model import BasePageModel
-from docling.utils.profiling import TimeRecorder
+from docowling.datamodel.base_models import Page
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.settings import settings
+from docowling.models.base_model import BasePageModel
+from docowling.utils.profiling import TimeRecorder
 
 
 class PagePreprocessingOptions(BaseModel):

docowling/models/rapid_ocr_model.py

@@ -4,17 +4,17 @@ from typing import Iterable
 import numpy
 from docling_core.types.doc import BoundingBox, CoordOrigin
 
-from docling.datamodel.base_models import OcrCell, Page
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import (
+from docowling.datamodel.base_models import OcrCell, Page
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import (
     AcceleratorDevice,
     AcceleratorOptions,
     RapidOcrOptions,
 )
-from docling.datamodel.settings import settings
-from docling.models.base_ocr_model import BaseOcrModel
-from docling.utils.accelerator_utils import decide_device
-from docling.utils.profiling import TimeRecorder
+from docowling.datamodel.settings import settings
+from docowling.models.base_ocr_model import BaseOcrModel
+from docowling.utils.accelerator_utils import decide_device
+from docowling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
 

docowling/models/table_structure_model.py

@@ -7,18 +7,18 @@ from docling_core.types.doc import BoundingBox, DocItemLabel, TableCell
 from docling_ibm_models.tableformer.data_management.tf_predictor import TFPredictor
 from PIL import ImageDraw
 
-from docling.datamodel.base_models import Page, Table, TableStructurePrediction
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import (
+from docowling.datamodel.base_models import Page, Table, TableStructurePrediction
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import (
     AcceleratorDevice,
     AcceleratorOptions,
     TableFormerMode,
     TableStructureOptions,
 )
-from docling.datamodel.settings import settings
-from docling.models.base_model import BasePageModel
-from docling.utils.accelerator_utils import decide_device
-from docling.utils.profiling import TimeRecorder
+from docowling.datamodel.settings import settings
+from docowling.models.base_model import BasePageModel
+from docowling.utils.accelerator_utils import decide_device
+from docowling.utils.profiling import TimeRecorder
 
 
 class TableStructureModel(BasePageModel):

docowling/models/tesseract_ocr_cli_model.py

@@ -9,12 +9,12 @@ from typing import Iterable, Optional, Tuple
 import pandas as pd
 from docling_core.types.doc import BoundingBox, CoordOrigin
 
-from docling.datamodel.base_models import Cell, OcrCell, Page
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import TesseractCliOcrOptions
-from docling.datamodel.settings import settings
-from docling.models.base_ocr_model import BaseOcrModel
-from docling.utils.profiling import TimeRecorder
+from docowling.datamodel.base_models import Cell, OcrCell, Page
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import TesseractCliOcrOptions
+from docowling.datamodel.settings import settings
+from docowling.models.base_ocr_model import BaseOcrModel
+from docowling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
 

docowling/models/tesseract_ocr_model.py

@@ -3,12 +3,12 @@ from typing import Iterable
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
 
-from docling.datamodel.base_models import Cell, OcrCell, Page
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import TesseractOcrOptions
-from docling.datamodel.settings import settings
-from docling.models.base_ocr_model import BaseOcrModel
-from docling.utils.profiling import TimeRecorder
+from docowling.datamodel.base_models import Cell, OcrCell, Page
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import TesseractOcrOptions
+from docowling.datamodel.settings import settings
+from docowling.models.base_ocr_model import BaseOcrModel
+from docowling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
 

docowling/pipeline/base_pipeline.py

@@ -7,20 +7,20 @@ from typing import Callable, Iterable, List
 
 from docling_core.types.doc import DoclingDocument, NodeItem
 
-from docling.backend.abstract_backend import AbstractDocumentBackend
-from docling.backend.pdf_backend import PdfDocumentBackend
-from docling.datamodel.base_models import (
+from docowling.backend.abstract_backend import AbstractDocumentBackend
+from docowling.backend.pdf_backend import PdfDocumentBackend
+from docowling.datamodel.base_models import (
     ConversionStatus,
     DoclingComponentType,
     ErrorItem,
     Page,
 )
-from docling.datamodel.document import ConversionResult, InputDocument
-from docling.datamodel.pipeline_options import PipelineOptions
-from docling.datamodel.settings import settings
-from docling.models.base_model import BaseEnrichmentModel
-from docling.utils.profiling import ProfilingScope, TimeRecorder
-from docling.utils.utils import chunkify
+from docowling.datamodel.document import ConversionResult, InputDocument
+from docowling.datamodel.pipeline_options import PipelineOptions
+from docowling.datamodel.settings import settings
+from docowling.models.base_model import BaseEnrichmentModel
+from docowling.utils.profiling import ProfilingScope, TimeRecorder
+from docowling.utils.utils import chunkify
 
 _log = logging.getLogger(__name__)
 

docowling/pipeline/simple_pipeline.py

@@ -1,14 +1,14 @@
 import logging
 
-from docling.backend.abstract_backend import (
+from docowling.backend.abstract_backend import (
     AbstractDocumentBackend,
     DeclarativeDocumentBackend,
 )
-from docling.datamodel.base_models import ConversionStatus
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import PipelineOptions
-from docling.pipeline.base_pipeline import BasePipeline
-from docling.utils.profiling import ProfilingScope, TimeRecorder
+from docowling.datamodel.base_models import ConversionStatus
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import PipelineOptions
+from docowling.pipeline.base_pipeline import BasePipeline
+from docowling.utils.profiling import ProfilingScope, TimeRecorder
 
 _log = logging.getLogger(__name__)
 

docowling/pipeline/standard_pdf_pipeline.py

@@ -5,11 +5,11 @@ from typing import Optional
 
 from docling_core.types.doc import DocItem, ImageRef, PictureItem, TableItem
 
-from docling.backend.abstract_backend import AbstractDocumentBackend
-from docling.backend.pdf_backend import PdfDocumentBackend
-from docling.datamodel.base_models import AssembledUnit, Page
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import (
+from docowling.backend.abstract_backend import AbstractDocumentBackend
+from docowling.backend.pdf_backend import PdfDocumentBackend
+from docowling.datamodel.base_models import AssembledUnit, Page
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import (
     EasyOcrOptions,
     OcrMacOptions,
     PdfPipelineOptions,
@@ -17,22 +17,22 @@ from docling.datamodel.pipeline_options import (
     TesseractCliOcrOptions,
     TesseractOcrOptions,
 )
-from docling.models.base_ocr_model import BaseOcrModel
-from docling.models.ds_glm_model import GlmModel, GlmOptions
-from docling.models.easyocr_model import EasyOcrModel
-from docling.models.layout_model import LayoutModel
-from docling.models.ocr_mac_model import OcrMacModel
-from docling.models.page_assemble_model import PageAssembleModel, PageAssembleOptions
-from docling.models.page_preprocessing_model import (
+from docowling.models.base_ocr_model import BaseOcrModel
+from docowling.models.ds_glm_model import GlmModel, GlmOptions
+from docowling.models.easyocr_model import EasyOcrModel
+from docowling.models.layout_model import LayoutModel
+from docowling.models.ocr_mac_model import OcrMacModel
+from docowling.models.page_assemble_model import PageAssembleModel, PageAssembleOptions
+from docowling.models.page_preprocessing_model import (
     PagePreprocessingModel,
     PagePreprocessingOptions,
 )
-from docling.models.rapid_ocr_model import RapidOcrModel
-from docling.models.table_structure_model import TableStructureModel
-from docling.models.tesseract_ocr_cli_model import TesseractOcrCliModel
-from docling.models.tesseract_ocr_model import TesseractOcrModel
-from docling.pipeline.base_pipeline import PaginatedPipeline
-from docling.utils.profiling import ProfilingScope, TimeRecorder
+from docowling.models.rapid_ocr_model import RapidOcrModel
+from docowling.models.table_structure_model import TableStructureModel
+from docowling.models.tesseract_ocr_cli_model import TesseractOcrCliModel
+from docowling.models.tesseract_ocr_model import TesseractOcrModel
+from docowling.pipeline.base_pipeline import PaginatedPipeline
+from docowling.utils.profiling import ProfilingScope, TimeRecorder
 
 _log = logging.getLogger(__name__)
 

docowling/utils/accelerator_utils.py

@@ -2,7 +2,7 @@ import logging
 
 import torch
 
-from docling.datamodel.pipeline_options import AcceleratorDevice
+from docowling.datamodel.pipeline_options import AcceleratorDevice
 
 _log = logging.getLogger(__name__)
 

docowling/utils/export.py

@@ -4,8 +4,8 @@ from typing import Any, Dict, Iterable, List, Tuple, Union
 from docling_core.types.doc import BoundingBox, CoordOrigin
 from docling_core.types.legacy_doc.base import BaseCell, BaseText, Ref, Table
 
-from docling.datamodel.base_models import OcrCell
-from docling.datamodel.document import ConversionResult, Page
+from docowling.datamodel.base_models import OcrCell
+from docowling.datamodel.document import ConversionResult, Page
 
 _log = logging.getLogger(__name__)
 

docowling/utils/layout_postprocessor.py

@@ -7,7 +7,7 @@ from typing import Dict, List, Set, Tuple
 from docling_core.types.doc import DocItemLabel, Size
 from rtree import index
 
-from docling.datamodel.base_models import BoundingBox, Cell, Cluster, OcrCell
+from docowling.datamodel.base_models import BoundingBox, Cell, Cluster, OcrCell
 
 _log = logging.getLogger(__name__)
 

docowling/utils/profiling.py

@@ -6,10 +6,10 @@ from typing import TYPE_CHECKING, List
 import numpy as np
 from pydantic import BaseModel
 
-from docling.datamodel.settings import settings
+from docowling.datamodel.settings import settings
 
 if TYPE_CHECKING:
-    from docling.datamodel.document import ConversionResult
+    from docowling.datamodel.document import ConversionResult
 
 
 class ProfilingScope(str, Enum):

docs/concepts/chunking.md

@@ -28,7 +28,7 @@ The `BaseChunker` base class API defines that any chunker should provide the fol
 
     - If you are using the `docling` package, you can import as follows:
         ```python
-        from docling.chunking import HybridChunker
+        from docowling.chunking import HybridChunker
         ```
     - If you are only using the `docling-core` package, you must ensure to install
         the `chunking` extra, e.g.

docs/examples/batch_convert.py

@@ -6,10 +6,10 @@ from typing import Iterable
 
 import yaml
 
-from docling.datamodel.base_models import ConversionStatus
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.settings import settings
-from docling.document_converter import DocumentConverter
+from docowling.datamodel.base_models import ConversionStatus
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.settings import settings
+from docowling.document_converter import DocumentConverter
 
 _log = logging.getLogger(__name__)
 

docs/examples/custom_convert.py

@@ -3,13 +3,13 @@ import logging
 import time
 from pathlib import Path
 
-from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.pipeline_options import PdfPipelineOptions
-from docling.document_converter import DocumentConverter, PdfFormatOption
-from docling.models.ocr_mac_model import OcrMacOptions
-from docling.models.tesseract_ocr_cli_model import TesseractCliOcrOptions
-from docling.models.tesseract_ocr_model import TesseractOcrOptions
+from docowling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.pipeline_options import PdfPipelineOptions
+from docowling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.models.ocr_mac_model import OcrMacOptions
+from docowling.models.tesseract_ocr_cli_model import TesseractCliOcrOptions
+from docowling.models.tesseract_ocr_model import TesseractOcrOptions
 
 _log = logging.getLogger(__name__)
 

docs/examples/develop_picture_enrichment.py

@@ -10,11 +10,11 @@ from docling_core.types.doc import (
     PictureItem,
 )
 
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.pipeline_options import PdfPipelineOptions
-from docling.document_converter import DocumentConverter, PdfFormatOption
-from docling.models.base_model import BaseEnrichmentModel
-from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.pipeline_options import PdfPipelineOptions
+from docowling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.models.base_model import BaseEnrichmentModel
+from docowling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
 
 
 class ExamplePictureClassifierPipelineOptions(PdfPipelineOptions):

docs/examples/export_figures.py

@@ -4,9 +4,9 @@ from pathlib import Path
 
 from docling_core.types.doc import ImageRefMode, PictureItem, TableItem
 
-from docling.datamodel.base_models import FigureElement, InputFormat, Table
-from docling.datamodel.pipeline_options import PdfPipelineOptions
-from docling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.datamodel.base_models import FigureElement, InputFormat, Table
+from docowling.datamodel.pipeline_options import PdfPipelineOptions
+from docowling.document_converter import DocumentConverter, PdfFormatOption
 
 _log = logging.getLogger(__name__)
 

docs/examples/export_multimodal.py

@@ -5,11 +5,11 @@ from pathlib import Path
 
 import pandas as pd
 
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.pipeline_options import PdfPipelineOptions
-from docling.document_converter import DocumentConverter, PdfFormatOption
-from docling.utils.export import generate_multimodal_pages
-from docling.utils.utils import create_hash
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.pipeline_options import PdfPipelineOptions
+from docowling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.utils.export import generate_multimodal_pages
+from docowling.utils.utils import create_hash
 
 _log = logging.getLogger(__name__)
 

docs/examples/export_tables.py

@@ -4,7 +4,7 @@ from pathlib import Path
 
 import pandas as pd
 
-from docling.document_converter import DocumentConverter
+from docowling.document_converter import DocumentConverter
 
 _log = logging.getLogger(__name__)
 

docs/examples/full_page_ocr.py

@@ -1,8 +1,8 @@
 from pathlib import Path
 
-from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.pipeline_options import (
+from docowling.backend.docling_parse_backend import DoclingParseDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.pipeline_options import (
     EasyOcrOptions,
     OcrMacOptions,
     PdfPipelineOptions,
@@ -10,7 +10,7 @@ from docling.datamodel.pipeline_options import (
     TesseractCliOcrOptions,
     TesseractOcrOptions,
 )
-from docling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.document_converter import DocumentConverter, PdfFormatOption
 
 
 def main():

docs/examples/hybrid_chunking.ipynb

@@ -37,7 +37,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from docling.document_converter import DocumentConverter\n",
+    "from docowling.document_converter import DocumentConverter\n",
     "\n",
     "DOC_SOURCE = \"../../tests/data/md/wiki.md\"\n",
     "\n",
@@ -68,7 +68,7 @@
    "source": [
     "from transformers import AutoTokenizer\n",
     "\n",
-    "from docling.chunking import HybridChunker\n",
+    "from docowling.chunking import HybridChunker\n",
     "\n",
     "EMBED_MODEL_ID = \"sentence-transformers/all-MiniLM-L6-v2\"\n",
     "MAX_TOKENS = 64\n",
@@ -404,7 +404,7 @@
     "    return tbl\n",
     "\n",
     "\n",
-    "db_uri = str(Path(mkdtemp()) / \"docling.db\")\n",
+    "db_uri = str(Path(mkdtemp()) / \"docowling.db\")\n",
     "index = make_lancedb_index(db_uri, doc.name, chunks, embed_model)\n",
     "\n",
     "sample_query = \"invent\"\n",

docs/examples/hybrid_rag_qdrant.ipynb

@@ -81,8 +81,8 @@
     "from docling_core.transforms.chunker import HierarchicalChunker\n",
     "from qdrant_client import QdrantClient\n",
     "\n",
-    "from docling.datamodel.base_models import InputFormat\n",
-    "from docling.document_converter import DocumentConverter"
+    "from docowling.datamodel.base_models import InputFormat\n",
+    "from docowling.document_converter import DocumentConverter"
    ]
   },
   {

docs/examples/minimal.py

@@ -1,4 +1,4 @@
-from docling.document_converter import DocumentConverter
+from docowling.document_converter import DocumentConverter
 
 source = "https://arxiv.org/pdf/2408.09869"  # document per local path or URL
 converter = DocumentConverter()

docs/examples/rag_haystack.ipynb

@@ -110,7 +110,7 @@
     "EXPORT_TYPE = ExportType.DOC_CHUNKS\n",
     "QUESTION = \"Which are the main AI models in Docling?\"\n",
     "TOP_K = 3\n",
-    "MILVUS_URI = str(Path(mkdtemp()) / \"docling.db\")"
+    "MILVUS_URI = str(Path(mkdtemp()) / \"docowling.db\")"
    ]
   },
   {
@@ -168,7 +168,7 @@
     "from haystack.components.writers import DocumentWriter\n",
     "from milvus_haystack import MilvusDocumentStore, MilvusEmbeddingRetriever\n",
     "\n",
-    "from docling.chunking import HybridChunker\n",
+    "from docowling.chunking import HybridChunker\n",
     "\n",
     "document_store = MilvusDocumentStore(\n",
     "    connection_args={\"uri\": MILVUS_URI},\n",
@@ -329,7 +329,7 @@
     }
    ],
    "source": [
-    "from docling.chunking import DocChunk\n",
+    "from docowling.chunking import DocChunk\n",
     "\n",
     "print(f\"Question:\\n{QUESTION}\\n\")\n",
     "print(f\"Answer:\\n{rag_res['answer_builder']['answers'][0].data.strip()}\\n\")\n",

docs/examples/rag_langchain.ipynb

@@ -83,7 +83,7 @@
     "from langchain_core.document_loaders import BaseLoader\n",
     "from langchain_core.documents import Document as LCDocument\n",
     "\n",
-    "from docling.document_converter import DocumentConverter\n",
+    "from docowling.document_converter import DocumentConverter\n",
     "\n",
     "class DoclingPDFLoader(BaseLoader):\n",
     "\n",

docs/examples/rag_llamaindex.ipynb

@@ -117,7 +117,7 @@
     "from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI\n",
     "\n",
     "EMBED_MODEL = HuggingFaceEmbedding(model_name=\"BAAI/bge-small-en-v1.5\")\n",
-    "MILVUS_URI = str(Path(mkdtemp()) / \"docling.db\")\n",
+    "MILVUS_URI = str(Path(mkdtemp()) / \"docowling.db\")\n",
     "GEN_MODEL = HuggingFaceInferenceAPI(\n",
     "    token=_get_env_from_colab_or_os(\"HF_TOKEN\"),\n",
     "    model_name=\"mistralai/Mixtral-8x7B-Instruct-v0.1\",\n",
@@ -182,7 +182,7 @@
     "node_parser = MarkdownNodeParser()\n",
     "\n",
     "vector_store = MilvusVectorStore(\n",
-    "    uri=str(Path(mkdtemp()) / \"docling.db\"),  # or set as needed\n",
+    "    uri=str(Path(mkdtemp()) / \"docowling.db\"),  # or set as needed\n",
     "    dim=embed_dim,\n",
     "    overwrite=True,\n",
     ")\n",
@@ -282,7 +282,7 @@
     "node_parser = DoclingNodeParser()\n",
     "\n",
     "vector_store = MilvusVectorStore(\n",
-    "    uri=str(Path(mkdtemp()) / \"docling.db\"),  # or set as needed\n",
+    "    uri=str(Path(mkdtemp()) / \"docowling.db\"),  # or set as needed\n",
     "    dim=embed_dim,\n",
     "    overwrite=True,\n",
     ")\n",
@@ -423,7 +423,7 @@
     ")\n",
     "\n",
     "vector_store = MilvusVectorStore(\n",
-    "    uri=str(Path(mkdtemp()) / \"docling.db\"),  # or set as needed\n",
+    "    uri=str(Path(mkdtemp()) / \"docowling.db\"),  # or set as needed\n",
     "    dim=embed_dim,\n",
     "    overwrite=True,\n",
     ")\n",

docs/examples/rag_weaviate.ipynb

@@ -207,8 +207,8 @@
     }
    ],
    "source": [
-    "from docling.datamodel.document import ConversionResult\n",
-    "from docling.document_converter import DocumentConverter\n",
+    "from docowling.datamodel.document import ConversionResult\n",
+    "from docowling.document_converter import DocumentConverter\n",
     "\n",
     "# Instantiate the doc converter\n",
     "doc_converter = DocumentConverter()\n",

docs/examples/run_md.py

@@ -5,9 +5,9 @@ from pathlib import Path
 
 import yaml
 
-from docling.backend.md_backend import MarkdownDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.backend.md_backend import MarkdownDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 

docs/examples/run_with_accelerator.py

@@ -1,16 +1,16 @@
 from pathlib import Path
 
-from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.pipeline_options import (
+from docowling.backend.docling_parse_backend import DoclingParseDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.pipeline_options import (
     AcceleratorDevice,
     AcceleratorOptions,
     PdfPipelineOptions,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
 )
-from docling.datamodel.settings import settings
-from docling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.datamodel.settings import settings
+from docowling.document_converter import DocumentConverter, PdfFormatOption
 
 
 def main():

docs/examples/run_with_formats.py

@@ -4,15 +4,15 @@ from pathlib import Path
 
 import yaml
 
-from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.document_converter import (
+from docowling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.document_converter import (
     DocumentConverter,
     PdfFormatOption,
     WordFormatOption,
 )
-from docling.pipeline.simple_pipeline import SimplePipeline
-from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
+from docowling.pipeline.simple_pipeline import SimplePipeline
+from docowling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
 
 _log = logging.getLogger(__name__)
 

docs/faq.md

@@ -140,7 +140,7 @@ This is a collection of FAQ collected from the user questions on <https://github
     Setting the OCR language in Docling is done via the OCR pipeline options:
 
     ```py
-    from docling.datamodel.pipeline_options import PdfPipelineOptions
+    from docowling.datamodel.pipeline_options import PdfPipelineOptions
 
     pipeline_options = PdfPipelineOptions()
     pipeline_options.ocr_options.lang = ["fr", "de", "es", "en"]  # example of languages for EasyOCR

docs/installation.md

@@ -36,9 +36,9 @@ Works on macOS, Linux, and Windows, with support for both x86_64 and arm64 archi
     The Docling `DocumentConverter` allows to choose the OCR engine with the `ocr_options` settings. For example
 
     ```python
-    from docling.datamodel.base_models import ConversionStatus, PipelineOptions
-    from docling.datamodel.pipeline_options import PipelineOptions, EasyOcrOptions, TesseractOcrOptions
-    from docling.document_converter import DocumentConverter
+    from docowling.datamodel.base_models import ConversionStatus, PipelineOptions
+    from docowling.datamodel.pipeline_options import PipelineOptions, EasyOcrOptions, TesseractOcrOptions
+    from docowling.document_converter import DocumentConverter
 
     pipeline_options = PipelineOptions()
     pipeline_options.do_ocr = True

docs/reference/cli.md

@@ -3,7 +3,7 @@
 This page provides documentation for our command line tools.
 
 ::: mkdocs-click
-    :module: docling.cli.main
+    :module: docowling.cli.main
     :command: click_app
     :prog_name: docling
     :style: table

docs/reference/document_converter.md

@@ -2,7 +2,7 @@
 
 This is an automatic generated API reference of the main components of Docling.
 
-::: docling.document_converter
+::: docowling.document_converter
     handler: python
     options:
         members:

docs/reference/pipeline_options.md

@@ -8,7 +8,7 @@ can be enabled with `do_xyz = True`.
 This is an automatic generated API reference of the all the pipeline options available in Docling.
 
 
-::: docling.datamodel.pipeline_options
+::: docowling.datamodel.pipeline_options
     handler: python
     options:
         show_if_no_docstring: true
@@ -28,7 +28,7 @@ This is an automatic generated API reference of the all the pipeline options ava
         signature_crossrefs: true
         summary: true
 
-<!-- ::: docling.document_converter.DocumentConverter
+<!-- ::: docowling.document_converter.DocumentConverter
     handler: python
     options:
         show_if_no_docstring: true

docs/usage.md

@@ -5,7 +5,7 @@
 To convert individual PDF documents, use `convert()`, for example:
 
 ```python
-from docling.document_converter import DocumentConverter
+from docowling.document_converter import DocumentConverter
 
 source = "https://arxiv.org/pdf/2408.09869"  # PDF path or URL
 converter = DocumentConverter()
@@ -39,9 +39,9 @@ This can improve output quality if you find that multiple columns in extracted t
 
 
 ```python
-from docling.datamodel.base_models import InputFormat
-from docling.document_converter import DocumentConverter, PdfFormatOption
-from docling.datamodel.pipeline_options import PdfPipelineOptions
+from docowling.datamodel.base_models import InputFormat
+from docowling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.datamodel.pipeline_options import PdfPipelineOptions
 
 pipeline_options = PdfPipelineOptions(do_table_structure=True)
 pipeline_options.table_structure_options.do_cell_matching = False  # uses text cells predicted from table structure model
@@ -56,9 +56,9 @@ doc_converter = DocumentConverter(
 Since docling 1.16.0: You can control which TableFormer mode you want to use. Choose between `TableFormerMode.FAST` (default) and `TableFormerMode.ACCURATE` (better, but slower) to receive better quality with difficult table structures.
 
 ```python
-from docling.datamodel.base_models import InputFormat
-from docling.document_converter import DocumentConverter, PdfFormatOption
-from docling.datamodel.pipeline_options import PdfPipelineOptions, TableFormerMode
+from docowling.datamodel.base_models import InputFormat
+from docowling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.datamodel.pipeline_options import PdfPipelineOptions, TableFormerMode
 
 pipeline_options = PdfPipelineOptions(do_table_structure=True)
 pipeline_options.table_structure_options.mode = TableFormerMode.ACCURATE  # use more accurate TableFormer model
@@ -75,10 +75,10 @@ doc_converter = DocumentConverter(
 By default, artifacts such as models are downloaded automatically upon first usage. If you would prefer to use a local path where the artifacts have been explicitly prefetched, you can do that as follows:
 
 ```python
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.pipeline_options import PdfPipelineOptions
-from docling.document_converter import DocumentConverter, PdfFormatOption
-from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.pipeline_options import PdfPipelineOptions
+from docowling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
 
 # # to explicitly prefetch:
 # artifacts_path = StandardPdfPipeline.download_models_hf()
@@ -99,7 +99,7 @@ You can limit the file size and number of pages which should be allowed to proce
 
 ```python
 from pathlib import Path
-from docling.document_converter import DocumentConverter
+from docowling.document_converter import DocumentConverter
 
 source = "https://arxiv.org/pdf/2408.09869"
 converter = DocumentConverter()
@@ -112,8 +112,8 @@ You can convert PDFs from a binary stream instead of from the filesystem as foll
 
 ```python
 from io import BytesIO
-from docling.datamodel.base_models import DocumentStream
-from docling.document_converter import DocumentConverter
+from docowling.datamodel.base_models import DocumentStream
+from docowling.document_converter import DocumentConverter
 
 buf = BytesIO(your_binary_stream)
 source = DocumentStream(name="my_doc.pdf", stream=buf)
@@ -133,8 +133,8 @@ You can chunk a Docling document using a [chunker](concepts/chunking.md), such a
 [this example](examples/hybrid_chunking.ipynb)):
 
 ```python
-from docling.document_converter import DocumentConverter
-from docling.chunking import HybridChunker
+from docowling.document_converter import DocumentConverter
+from docowling.chunking import HybridChunker
 
 conv_res = DocumentConverter().convert("https://arxiv.org/pdf/2206.01062")
 doc = conv_res.document

docs/v2.md

@@ -46,17 +46,17 @@ Format options can include the pipeline class to use, the options to provide to
 They are provided as format-specific types, such as `PdfFormatOption` or `WordFormatOption`, as seen below.
 
 ```python
-from docling.document_converter import DocumentConverter
-from docling.datamodel.base_models import InputFormat
-from docling.document_converter import (
+from docowling.document_converter import DocumentConverter
+from docowling.datamodel.base_models import InputFormat
+from docowling.document_converter import (
     DocumentConverter,
     PdfFormatOption,
     WordFormatOption,
 )
-from docling.pipeline.simple_pipeline import SimplePipeline
-from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
-from docling.datamodel.pipeline_options import PdfPipelineOptions
-from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
+from docowling.pipeline.simple_pipeline import SimplePipeline
+from docowling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
+from docowling.datamodel.pipeline_options import PdfPipelineOptions
+from docowling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
 
 ## Default initialization still works as before:
 # doc_converter = DocumentConverter()
@@ -110,7 +110,7 @@ or `DocumentStream` objects, without constructing a `DocumentConversionInput` ob
 
 ```python
 ...
-from docling.datamodel.document import ConversionResult
+from docowling.datamodel.document import ConversionResult
 ## Convert a single file (from URL or local path)
 conv_result: ConversionResult = doc_converter.convert("https://arxiv.org/pdf/2408.09869") # previously `convert_single`
 

pyproject.toml

@@ -118,7 +118,7 @@ ocrmac = ["ocrmac"]
 rapidocr = ["rapidocr-onnxruntime", "onnxruntime"]
 
 [tool.poetry.scripts]
-docling = "docling.cli.main:app"
+docling = "docowling.cli.main:app"
 
 [build-system]
 requires = ["poetry-core"]

tests/test_backend_asciidoc.py

@@ -2,9 +2,9 @@ import glob
 import os
 from pathlib import Path
 
-from docling.backend.asciidoc_backend import AsciiDocBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.backend.asciidoc_backend import AsciiDocBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 
 def _get_backend(fname):

tests/test_backend_docling_parse.py

@@ -3,12 +3,12 @@ from pathlib import Path
 import pytest
 from docling_core.types.doc import BoundingBox
 
-from docling.backend.docling_parse_backend import (
+from docowling.backend.docling_parse_backend import (
     DoclingParseDocumentBackend,
     DoclingParsePageBackend,
 )
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 
 @pytest.fixture

tests/test_backend_docling_parse_v2.py

@@ -2,12 +2,12 @@ from pathlib import Path
 
 import pytest
 
-from docling.backend.docling_parse_v2_backend import (
+from docowling.backend.docling_parse_v2_backend import (
     DoclingParseV2DocumentBackend,
     DoclingParseV2PageBackend,
 )
-from docling.datamodel.base_models import BoundingBox, InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.datamodel.base_models import BoundingBox, InputFormat
+from docowling.datamodel.document import InputDocument
 
 
 @pytest.fixture

tests/test_backend_html.py

@@ -2,14 +2,14 @@ import json
 import os
 from pathlib import Path
 
-from docling.backend.html_backend import HTMLDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import (
+from docowling.backend.html_backend import HTMLDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import (
     ConversionResult,
     InputDocument,
     SectionHeaderItem,
 )
-from docling.document_converter import DocumentConverter
+from docowling.document_converter import DocumentConverter
 
 GENERATE = False
 

tests/test_backend_msexcel.py

@@ -2,14 +2,14 @@ import json
 import os
 from pathlib import Path
 
-from docling.backend.msword_backend import MsWordDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import (
+from docowling.backend.msword_backend import MsWordDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import (
     ConversionResult,
     InputDocument,
     SectionHeaderItem,
 )
-from docling.document_converter import DocumentConverter
+from docowling.document_converter import DocumentConverter
 
 GENERATE = False
 

tests/test_backend_msword.py

@@ -2,14 +2,14 @@ import json
 import os
 from pathlib import Path
 
-from docling.backend.msword_backend import MsWordDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import (
+from docowling.backend.msword_backend import MsWordDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import (
     ConversionResult,
     InputDocument,
     SectionHeaderItem,
 )
-from docling.document_converter import DocumentConverter
+from docowling.document_converter import DocumentConverter
 
 GENERATE = False
 

tests/test_backend_patent_uspto.py

@@ -1,4 +1,4 @@
-"""Test methods in module docling.backend.patent_uspto_backend.py."""
+"""Test methods in module docowling.backend.patent_uspto_backend.py."""
 
 import json
 import logging
@@ -12,14 +12,14 @@ import yaml
 from docling_core.types import DoclingDocument
 from docling_core.types.doc import DocItemLabel, TableData, TextItem
 
-from docling.backend.xml.uspto_backend import PatentUsptoDocumentBackend, XmlTable
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import (
+from docowling.backend.xml.uspto_backend import PatentUsptoDocumentBackend, XmlTable
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import (
     ConversionResult,
     InputDocument,
     SectionHeaderItem,
 )
-from docling.document_converter import DocumentConverter
+from docowling.document_converter import DocumentConverter
 
 GENERATE: bool = True
 DATA_PATH: Path = Path("./tests/data/uspto/")

tests/test_backend_pdfium.py

@@ -3,12 +3,12 @@ from pathlib import Path
 import pytest
 from docling_core.types.doc import BoundingBox
 
-from docling.backend.pypdfium2_backend import (
+from docowling.backend.pypdfium2_backend import (
     PyPdfiumDocumentBackend,
     PyPdfiumPageBackend,
 )
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import InputDocument
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import InputDocument
 
 
 @pytest.fixture

tests/test_backend_pptx.py

@@ -2,9 +2,9 @@ import json
 import os
 from pathlib import Path
 
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import ConversionResult
-from docling.document_converter import DocumentConverter
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import ConversionResult
+from docowling.document_converter import DocumentConverter
 
 GENERATE = False
 

tests/test_backend_pubmed.py

@@ -6,9 +6,9 @@ from pathlib import Path
 
 from docling_core.types.doc import DoclingDocument
 
-from docling.datamodel.base_models import DocumentStream, InputFormat
-from docling.datamodel.document import ConversionResult
-from docling.document_converter import DocumentConverter
+from docowling.datamodel.base_models import DocumentStream, InputFormat
+from docowling.datamodel.document import ConversionResult
+from docowling.document_converter import DocumentConverter
 
 GENERATE = False
 

tests/test_cli.py

@@ -2,7 +2,7 @@ from pathlib import Path
 
 from typer.testing import CliRunner
 
-from docling.cli.main import app
+from docowling.cli.main import app
 
 runner = CliRunner()
 

tests/test_e2e_conversion.py

@@ -1,10 +1,10 @@
 from pathlib import Path
 
-from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import PdfPipelineOptions
-from docling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.backend.docling_parse_backend import DoclingParseDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import PdfPipelineOptions
+from docowling.document_converter import DocumentConverter, PdfFormatOption
 
 from .verify_utils import verify_conversion_result_v1, verify_conversion_result_v2
 

tests/test_e2e_ocr_conversion.py

@@ -2,10 +2,10 @@ import sys
 from pathlib import Path
 from typing import List
 
-from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import (
+from docowling.backend.docling_parse_backend import DoclingParseDocumentBackend
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import (
     EasyOcrOptions,
     OcrMacOptions,
     OcrOptions,
@@ -14,7 +14,7 @@ from docling.datamodel.pipeline_options import (
     TesseractCliOcrOptions,
     TesseractOcrOptions,
 )
-from docling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.document_converter import DocumentConverter, PdfFormatOption
 
 from .verify_utils import verify_conversion_result_v1, verify_conversion_result_v2
 

tests/test_input_doc.py

@@ -1,9 +1,9 @@
 from io import BytesIO
 from pathlib import Path
 
-from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
-from docling.datamodel.base_models import DocumentStream, InputFormat
-from docling.datamodel.document import InputDocument, _DocumentConversionInput
+from docowling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
+from docowling.datamodel.base_models import DocumentStream, InputFormat
+from docowling.datamodel.document import InputDocument, _DocumentConversionInput
 
 
 def test_in_doc_from_valid_path():
@@ -40,7 +40,7 @@ def test_in_doc_from_invalid_buf():
 
 
 def test_guess_format(tmp_path):
-    """Test docling.datamodel.document._DocumentConversionInput.__guess_format"""
+    """Test docowling.datamodel.document._DocumentConversionInput.__guess_format"""
     dci = _DocumentConversionInput(path_or_stream_iterator=[])
     temp_dir = tmp_path / "test_guess_format"
     temp_dir.mkdir()

tests/test_interfaces.py

@@ -3,10 +3,10 @@ from pathlib import Path
 
 import pytest
 
-from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
-from docling.datamodel.base_models import DocumentStream, InputFormat
-from docling.datamodel.pipeline_options import PdfPipelineOptions
-from docling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.backend.docling_parse_backend import DoclingParseDocumentBackend
+from docowling.datamodel.base_models import DocumentStream, InputFormat
+from docowling.datamodel.pipeline_options import PdfPipelineOptions
+from docowling.document_converter import DocumentConverter, PdfFormatOption
 
 from .verify_utils import verify_conversion_result_v1, verify_conversion_result_v2
 

tests/test_invalid_input.py

@@ -3,8 +3,8 @@ from pathlib import Path
 
 import pytest
 
-from docling.datamodel.base_models import ConversionStatus, DocumentStream
-from docling.document_converter import ConversionError, DocumentConverter
+from docowling.datamodel.base_models import ConversionStatus, DocumentStream
+from docowling.document_converter import ConversionError, DocumentConverter
 
 
 def get_pdf_path():

tests/test_legacy_format_transform.py

@@ -3,9 +3,9 @@ from pathlib import Path
 
 import pytest
 
-from docling.datamodel.base_models import InputFormat
-from docling.datamodel.pipeline_options import PdfPipelineOptions
-from docling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.datamodel.base_models import InputFormat
+from docowling.datamodel.pipeline_options import PdfPipelineOptions
+from docowling.document_converter import DocumentConverter, PdfFormatOption
 
 
 @pytest.fixture

tests/test_options.py

@@ -3,16 +3,16 @@ from pathlib import Path
 
 import pytest
 
-from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
-from docling.datamodel.base_models import ConversionStatus, InputFormat
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import (
+from docowling.backend.docling_parse_backend import DoclingParseDocumentBackend
+from docowling.datamodel.base_models import ConversionStatus, InputFormat
+from docowling.datamodel.document import ConversionResult
+from docowling.datamodel.pipeline_options import (
     AcceleratorDevice,
     AcceleratorOptions,
     PdfPipelineOptions,
     TableFormerMode,
 )
-from docling.document_converter import DocumentConverter, PdfFormatOption
+from docowling.document_converter import DocumentConverter, PdfFormatOption
 
 
 @pytest.fixture

tests/verify_utils.py

@@ -8,8 +8,8 @@ from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocu
 from pydantic import TypeAdapter
 from pydantic.json import pydantic_encoder
 
-from docling.datamodel.base_models import ConversionStatus, Page
-from docling.datamodel.document import ConversionResult
+from docowling.datamodel.base_models import ConversionStatus, Page
+from docowling.datamodel.document import ConversionResult
 
 
 def levenshtein(str1: str, str2: str) -> int: